AI enrichments allow you to automatically generate or refine product attributes, creating Smart Attributes to optimize your data efficiently. For more information, refer to our Smart Attributes guide.
To learn how to set up AI enrichments, visit our step-by-step guide, and for common questions, check out the Smart Attributes FAQ.
In this article, you’ll find answers to the most common questions about Smart Attributes and AI enrichments in Channable. From understanding what Smart Attributes are to managing AI-generated data, this FAQ will guide you through key concepts and features to help you optimize your product data efficiently.
Table of contents
- What is the Optimize tab?
- What are Smart Attributes?
- What is an AI enrichment?
- Which product attributes can AI enrichments generate?
- Where are AI enrichments placed?
- Can I approve AI-generated Smart Attributes?
- How do I limit AI enrichments to specific items?
- How can I regenerate AI enrichments?
- Where do I store Smart Attributes?
- Why do some items have the wrong value?
- How can I change the language of the generated results?
What is the Optimize tab?
The Optimize tab in Channable is the home of Smart Attributes. The Smart Attributes tab within the Optimize tab is where you can create and manage AI enrichments to improve your product data. In the future we will expand with more AI related features which you can then find here, as well.
What are Smart Attributes?
Smart Attributes are product attributes that are automatically generated or refined using AI enrichments in Channable. These attributes help optimize your data and make it easier to meet marketplace requirements.
What is an AI enrichment?
AI enrichment is the process of automatically generating or refining product attributes by analyzing your imported data. The final result of an AI enrichment is a Smart Attribute, which helps improve product data quality with minimal manual input.
Which product attributes can AI enrichments generate?
AI enrichments can generate or refine the attributes listed below.
- Color
- Weight
- Quantity
- Brand
- Length
- Width
- Height
- Volume
- Material
- Keywords
Where are AI enrichments placed?
AI enrichments are applied after the import process is completed. Once the product data is imported, the AI generates or refines product attributes based on the AI Rules set. The resulting Smart Attributes are then merged with the imported data for use in feeds, exports, and channels.
Can I approve AI-generated Smart Attributes?
Yes, once AI generates Smart Attributes, you can review and approve the results. You can approve all results at once or approve each one individually before they are used in your project.
How do I limit AI enrichments to specific items?
You can use the Targeting feature to specify which items the AI should enrich. This is useful if you want to focus on specific categories or brands to keep generation faster and more precise.
How can I regenerate AI enrichments?
You can regenerate AI enrichments at any time by using the Regenerate button. This allows the AI to process the latest data and update the generated attributes accordingly.
Where do I store Smart Attributes?
When configuring an AI enrichment, you can choose where to store the generated attributes. You can save them in an existing field or create a new one to avoid overwriting existing data.
Why do some items have the wrong value?
AI enrichments rely on the Unique ID per item set in your project settings. If two or more items share the same Unique ID, this can cause the AI to generate the same attribute values for those items, even if they are different products. To avoid this, ensure that each item has a distinct Unique ID.
Additionally, incorrect values may occur if the AI cannot accurately interpret the data from the selected fields. Make sure that the fields you selected for the AI to search in contain the relevant information for the attribute you are enriching.
How can I change the language of the generated results?
In the AI enrichment settings, you can select the Output language option. By default, the results are generated in the same language as your input data, but you can choose to translate the generated attributes into a different language using this setting.